Imagen de Portada

Free Lunch for Pass@$k$? Low Cost Diverse Sampling for Diffusion Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lamont, Sean, Walder, Christian, Montague, Paul, Dezfouli, Amir, Norrish, Michael
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

3D-Prover: Diversity Driven Theorem Proving With Determinantal Point Processes
por: Lamont, Sean, et al.
Publicado: (2024)

BAIT: Benchmarking (Embedding) Architectures for Interactive Theorem-Proving
por: Lamont, Sean, et al.
Publicado: (2024)

Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems
por: Walder, Christian, et al.
Publicado: (2025)

Cost-of-Pass: An Economic Framework for Evaluating Language Models
por: Erol, Mehmet Hamza, et al.
Publicado: (2025)

Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
por: Qin, Zhen, et al.
Publicado: (2024)

Asking LLMs to Verify First is Almost Free Lunch
por: Wu, Shiguang, et al.
Publicado: (2025)

Is It a Free Lunch for Removing Outliers during Pretraining?
por: Liao, Baohao, et al.
Publicado: (2024)

Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models
por: Wu, Jingxuan, et al.
Publicado: (2026)

No Free Lunch in Language Model Bias Mitigation? Targeted Bias Reduction Can Exacerbate Unmitigated LLM Biases
por: Chand, Shireen, et al.
Publicado: (2025)

LLMInit: A Free Lunch from Large Language Models for Selective Initialization of Recommendation
por: Zhang, Weizhi, et al.
Publicado: (2025)

Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation
por: Hariri, Mohsen, et al.
Publicado: (2025)

Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
por: Bi, Baolong, et al.
Publicado: (2024)

Residual Context Diffusion Language Models
por: Hu, Yuezhou, et al.
Publicado: (2026)

MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Cost
por: Xing, Sen, et al.
Publicado: (2024)

No Free Lunch in Active Learning: LLM Embedding Quality Dictates Query Strategy Success
por: Rauch, Lukas, et al.
Publicado: (2025)

Luna: An Evaluation Foundation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost
por: Belyi, Masha, et al.
Publicado: (2024)

Optimizing Temperature for Language Models with Multi-Sample Inference
por: Du, Weihua, et al.
Publicado: (2025)

Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models
por: Chen, Zhipeng, et al.
Publicado: (2025)

Leveraging LLM Inconsistency to Boost Pass@k Performance
por: Dalal, Uri, et al.
Publicado: (2025)

CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs
por: Li, Haoran, et al.
Publicado: (2026)

Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling
por: Aynetdinov, Ansar, et al.
Publicado: (2026)

Understanding the Quality-Diversity Trade-off in Diffusion Language Models
por: Buzzard, Zak
Publicado: (2025)

DiffusionDialog: A Diffusion Model for Diverse Dialog Generation with Latent Space
por: Xiang, Jianxiang, et al.
Publicado: (2024)

BEFT: Bias-Efficient Fine-Tuning of Language Models in Low-Data Regimes
por: Huang, Baichuan, et al.
Publicado: (2025)

FoodSky: A Food-oriented Large Language Model that Passes the Chef and Dietetic Examination
por: Zhou, Pengfei, et al.
Publicado: (2024)

Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes
por: Christ, Bryan R., et al.
Publicado: (2024)

A Statistical Physics of Language Model Reasoning
por: Carson, Jack David, et al.
Publicado: (2025)

AI Diffusion in Low Resource Language Countries
por: Misra, Amit, et al.
Publicado: (2025)

MCSD: An Efficient Language Model with Diverse Fusion
por: Yang, Hua, et al.
Publicado: (2024)

Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity
por: Zhang, Jiayi, et al.
Publicado: (2025)

MyCulture: Exploring Malaysia's Diverse Culture under Low-Resource Language Constraints
por: Hew, Zhong Ken, et al.
Publicado: (2025)

No Reliable Evidence of Self-Reported Sentience in Small Large Language Models
por: Kaiser, Caspar, et al.
Publicado: (2026)

Reasoning Transfer for an Extremely Low-Resource and Endangered Language: Bridging Languages Through Sample-Efficient Language Understanding
por: Tran, Khanh-Tung, et al.
Publicado: (2025)

Reversible Diffusion Decoding for Diffusion Language Models
por: Wang, Xinyun, et al.
Publicado: (2026)

Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts
por: Nguyen, Xuan-Phi, et al.
Publicado: (2023)

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models
por: Shi, Haizhou, et al.
Publicado: (2024)

Scale-Free Graph-Language Models
por: Lu, Jianglin, et al.
Publicado: (2025)

Exploring the Learning Capabilities of Language Models using LEVERWORLDS
por: Wagner, Eitan, et al.
Publicado: (2024)

Semantic-guided Diverse Decoding for Large Language Model
por: Shi, Weijie, et al.
Publicado: (2025)

Overview of the First Workshop on Language Models for Low-Resource Languages (LoResLM 2025)
por: Hettiarachchi, Hansi, et al.
Publicado: (2024)